Investor runs 10,000 AI-generated scenarios on CAVA with SuperAnalyst and Canalyst models
RihardJarc · x · 2026-11-06
An investor demoed an agentic research stack: after seeing CAVA down 10%, his AlphaSense skill produced forecasts, peer comparisons, store growth/penetration analysis and sensitivities the way he'd do it manually. He then had SuperAnalyst drive Canalyst models as a tool, running 10,000 scenario paths like a weather forecast.
Charts show FY26–FY31 revenue and Adj. EBITDA cones (FY31 EBITDA: 10th pct $380m, median $571m, 90th pct $697m vs $625m base), plus the five-year IRR distribution from $54.67: 15–20% band 31.4%, 10–15% 24.2%, <0% only 9.6%. His takeaway: start from a drivable model plus forecasting and investment-analysis skills, then scale — "and this is the worst it's ever going to be." Not investment advice.
More from coding & agent
- Developer drives software factories and cloud agents via Slack, rarely opens a terminal — vikvang1 · 2026-11-06
- Glasshand rents real iPhones and Macs so AI agents can tap, type and swipe like humans — jia_seed · 2026-11-06
- UE6 drops Blueprints and C++ for Verse and AI prompts, but taste remains the hard part — AIandDesign · 2026-11-06
- Exo paper: agents that rewrite their own harness at runtime, cutting model cost up to 82% — sarahcat21 · 2026-11-06
- Study: LLMs Notice Context Conflicts 73% of the Time but Tell Users 0% — rseroter · 2026-11-06
- Ampersand matches frontier coding models at 70% lower cost via co-coding training — niloofar_mire · 2026-11-06